Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urança
    -0.07
     rein
    -0.07
     United
    -0.06
    edge
    -0.06
    PropertyName
    -0.06
     trừ
    -0.06
     kunt
    -0.06
     trousers
    -0.06
     fetus
    -0.06
     lapse
    -0.06
    POSITIVE LOGITS
    шим
    0.06
     �
    0.06
    하였
    0.06
     Illustr
    0.06
    ोव
    0.06
     adore
    0.06
     vy
    0.06
     erotiske
    0.06
    RefPtr
    0.06
    odon
    0.06
    Act Density 0.007%

    No Known Activations